© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111868
    Prev
    Next
    INDEX
    Explanations

    This Republic Back two leave secure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    -1.57
     заказать
    -1.45
    8
    -1.31
     there
    -1.27
    9
    -1.27
     подобрать
    -1.20
     then
    -1.18
    après
    -1.18
     приготовить
    -1.18
    껏
    -1.16
    POSITIVE LOGITS
     that
    1.76
     licorne
    1.53
     huge
    1.51
     jūsų
    1.48
    niaus
    1.46
    šnje
    1.43
     with
    1.41
     mūsų
    1.39
    īgs
    1.38
     aanbied
    1.37
    Activations Density 0.085%

    No Known Activations